Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    operation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Returned
    -0.07
     chiefly
    -0.06
     deposition
    -0.06
     predictable
    -0.06
     Records
    -0.06
    �
    -0.06
     trees
    -0.06
    	ret
    -0.06
     relief
    -0.05
    aj
    -0.05
    POSITIVE LOGITS
    _OM
    0.07
     deix
    0.07
    EFR
    0.07
     Sym
    0.06
     trata
    0.06
    Israel
    0.06
    %">↵
    0.06
     Zw
    0.06
    ...)↵
    0.06
    alted
    0.06
    Act Density 0.010%

    No Known Activations